Portrait de Ruth Crasto n'est pas disponible

Ruth Crasto

ruth.crasto@mila.quebec
Doctorat - McGill
Superviseur⋅e principal⋅e
David Rolnick
Sujets de recherche
Apprentissage de représentations
Apprentissage multimodal
Apprentissage profond
IA pour l'humanité
IA pour le changement climatique
Télédétection
Google Scholar

Publications

Localized, High-resolution Geographic Representations with Slepian Functions
Arjun Rao
Ruth Crasto
Tessa Ooms
David Rolnick
Konstantin Klemmer
Marc Rußwurm
Geographic data is fundamentally local. Disease outbreaks cluster in population centers, ecological patterns emerge along coastlines, and ec… (voir plus)onomic activity concentrates within country borders. Machine learning models that encode geographic location, however, distribute representational capacity uniformly across the globe, struggling at the fine-grained resolutions that localized applications require. We propose a geographic location encoder built from spherical Slepian functions that concentrate representational capacity inside a region-of-interest and scale to high resolutions without extensive computational demands. For settings requiring global context, we present a hybrid Slepian-Spherical Harmonic encoder that efficiently bridges the tradeoff between local-global performance, while retaining desirable properties such as pole-safety and spherical-surface-distance preservation. Across five tasks spanning classification, regression, and image-augmented prediction, Slepian encodings outperform baselines and retain performance advantages across a wide range of neural network architectures.
2026-01-29
arXiv (prépublication)
doi.org
arxiv.org